Xunlei Chen

Gaussian Core LoRA achieves a 7.95% reduction in attack success rates while maintaining visual quality, revolutionizing how we handle complex concept erasure in diffusion models.

Unlearning sensitive information in LLMs can be achieved without sacrificing performance, with ADU preserving up to 98% of model utility while effectively forgetting.

ST$^2$U reduces restricted-knowledge re-entry by up to 45% while preserving model capabilities, reshaping how we approach test-time unlearning in language models.

Achieve >95% forget quality in LLMs with minimal side effects by isolating and unlearning tokens within target subdomains using asymmetric LoRA.